TempCompass: leaderboard
Temporal reasoning benchmark for video LLMs testing understanding of temporal dynamics, ordering, and duration in videos.
Metric: Avg All (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 30 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 73.75 | #343 |
| 2 | Qwen 2 VL 7B Instruct | 67.85 | #826 |
| 3 | Gemini 1.5 Pro | 67.1 | #445 |
| 4 | MiniCPM-V-2.6 | 66.26 | #836 |
| 5 | InternVL2-8B | 66.03 | #817 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=tempcompass · How It Works · Data refreshed daily, snapshot 2026-10-20.